Distance learning from projective measurements as an information-geometric probe of many-body physics

• URL: http://arxiv.org/abs/2603.13485v1
• Date: Fri, 13 Mar 2026 18:03:28 GMT
• Title: Distance learning from projective measurements as an information-geometric probe of many-body physics
• Abstract summary: Modern quantum simulators generate large ensembles of single-shot projective "snapshots"<n>We forgo such representation learning in favour of distance learning.<n>We use a single neural discriminator to estimate Csiszar f-divergences--statistical distances between distributions--in an unsupervised manner.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The ability of modern quantum simulators--both digital and analogue--to generate large ensembles of single-shot projective "snapshots" has opened a data-rich avenue for the study of quantum many-body systems. Unsupervised machine learning analysis of such snapshots has gained traction, with numerous works reconstructing phase diagrams by learning and clustering low-dimensional representations of quantum states. Here, we forgo such representation learning in favour of distance learning: we infer the pairwise distances between quantum states--already sufficient for clustering--directly from snapshots. Specifically, we use a single neural discriminator to estimate Csiszar f-divergences--statistical distances between distributions--in an unsupervised manner. The resulting clusters reveal regimes with different dominant correlations, often coinciding with, but not limited to, conventionally defined phases of matter. Beyond phase-diagram exploration, we connect the infinitesimal limit of the inferred divergences to the Fisher information metric and analyse its finite-size scaling. This yields critical exponents of the discovered transitions and enables snapshot-based analysis of universality classes. We apply distance learning to a diverse set of systems characterised by conventional local order parameters (1D transverse-field and 2D classical Ising models), non-local topological order (extended toric code), and higher-order correlations (fermionic t-J model on a triangular lattice). In all cases, we correctly recover boundaries between distinct correlation regimes and, where applicable, quantitatively match established critical behaviour. Finally, we show that distances to suitably chosen reference snapshot distributions help identify the dominant correlations within the discovered clusters, positioning distance learning as a versatile information-geometric probe of quantum many-body physics.

Related papers

• Learning Orthogonal Multi-Index Models Beyond Small Initialization: Incremental Learning, Competitive Dynamics and Symmetry [52.75288960194919]
  Recent work has identified incremental learning in shallow networks trained on single-index and multi-index models.<n>We introduce a symmetry-based finite-width approximation via symmetrized networks, rather than comparing directly with an infinite-width limit.
  arXiv  Detail & Related papers  (2026-09-09T22:35:31Z)
• Post-Selection-Free Decoding of Measurement-Induced Area-Law Phases via Neural Networks [5.626168552306134]
  We devise a neural network architecture combining a convolutional neural network with an attention mechanism to classify trivial, long-range entangled, and symmetry-protected topological phases.<n>We show that the system's relaxation to a steady-state phase manifests as a sharp convergence in the classifier's accuracy, entirely bypassing the need for quantum state reconstruction.
  arXiv  Detail & Related papers  (2026-04-04T02:34:58Z)
• Distributed Phase-Insensitive Displacement Sensing [0.0]
  We study a phase-insensitive regime for bosonic sensors that undergo identical displacements with common phases randomly varying between experimental runs.<n>We derive analytical bounds on the achievable precision and show that it is determined by first-order normal correlations between modes in the probe state.<n>Our results are relevant to multimode continuous platforms, including trapped-ion, solid-state mechanical, optomechanical, superconducting, and photonic systems.
  arXiv  Detail & Related papers  (2026-02-03T16:45:58Z)
• GeoMM: On Geodesic Perspective for Multi-modal Learning [55.41612200877861]
  This paper introduces geodesic distance as a novel distance metric in multi-modal learning for the first time.<n>Our approach incorporates a comprehensive series of strategies to adapt geodesic distance for the current multimodal learning.
  arXiv  Detail & Related papers  (2025-05-16T13:12:41Z)
• Learning quantum properties from short-range correlations using multi-task networks [3.7228085662092845]
  We introduce a neural network model that can predict various quantum properties of many-body quantum states with constant correlation length. The model is based on the technique of multi-task learning, which we show to offer several advantages over traditional single-task approaches.
  arXiv  Detail & Related papers  (2023-10-18T08:53:23Z)
• Information Bounds on phase transitions in disordered systems [0.0]
  We study phase transitions in models with randomness, such as localization in disordered systems, or random quantum circuits with measurements. We benchmark our method and rederive the well-known Harris criterion, bounding critical exponents in the Anderson localization transition for noninteracting particles. While in real space our critical exponent bound agrees with recent consensus, we find that, somewhat surprisingly, numerical results on Fock-space localization for limited-sized systems do not obey our bounds.
  arXiv  Detail & Related papers  (2023-08-29T18:00:07Z)
• Evolution of many-body systems under ancilla quantum measurements [58.720142291102135]
  We study the concept of implementing quantum measurements by coupling a many-body lattice system to an ancillary degree of freedom. We find evidence of a disentangling-entangling measurement-induced transition as was previously observed in more abstract models.
  arXiv  Detail & Related papers  (2023-03-13T13:06:40Z)
• Deep learning of spatial densities in inhomogeneous correlated quantum systems [0.0]
  We show that we can learn to predict densities using convolutional neural networks trained on random potentials. We show that our approach can handle well the interplay of interference and interactions and the behaviour of models with phase transitions in inhomogeneous situations.
  arXiv  Detail & Related papers  (2022-11-16T17:10:07Z)
• Scalable approach to many-body localization via quantum data [69.3939291118954]
  Many-body localization is a notoriously difficult phenomenon from quantum many-body physics. We propose a flexible neural network based learning approach that circumvents any computationally expensive step. Our approach can be applied to large-scale quantum experiments to provide new insights into quantum many-body physics.
  arXiv  Detail & Related papers  (2022-02-17T19:00:09Z)
• Generalized quantum measurements with matrix product states: Entanglement phase transition and clusterization [58.720142291102135]
  We propose a method for studying the time evolution of many-body quantum lattice systems under continuous and site-resolved measurement. We observe a peculiar phenomenon of measurement-induced particle clusterization that takes place only for frequent moderately strong measurements, but not for strong infrequent measurements.
  arXiv  Detail & Related papers  (2021-04-21T10:36:57Z)
• Bayesian Sparse Factor Analysis with Kernelized Observations [67.60224656603823]
  Multi-view problems can be faced with latent variable models. High-dimensionality and non-linear issues are traditionally handled by kernel methods. We propose merging both approaches into single model.
  arXiv  Detail & Related papers  (2020-06-01T14:25:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.